Lead Data Scientist

Pareto Health is redefining the way employers fund healthcare. As the largest and fastest-growing benefits captive in the United States, we help thousands of small and midsize employers take control of healthcare costs through a smarter, more sustainable model.

Our mission is simple: give small and midsize employers the scale and protection they need to eliminate volatility and lower healthcare costs.

By combining data-driven insights, innovative risk management, and the collective purchasing power of our community, we enable employers to reduce volatility, improve long-term outcomes, and reinvest savings into their businesses and their people.

Headquartered in Philadelphia, Pareto Health is growing rapidly and transforming one of the country's largest industries. Our success is fueled by talented people who are united by our four core values:
Fire in the Belly, For the Greater Good, See the Field, and Get It Done Right. These values shape how we innovate, collaborate, make decisions, and deliver exceptional results for our clients and one another.

If you're energized by solving complex challenges, thrive in a high-growth environment, and want to help reshape the future of healthcare, we'd love to meet you.

Please note that Pareto Health does not provide employment visa sponsorship for this position. Candidates must be authorized to work in the United States without sponsorship both now or in the future.

Position Summary:

The Lead Data Scientist will independently lead applied AI and data science work streams that translate complex healthcare and underwriting data into measurable improvements in risk selection, pricing accuracy, operational efficiency, and the underwriting experience. The role will personally lead work from problem framing, target definition, feature engineering, and model development through rigorous validation, production deployment, monitoring, and business-impact measurement. The Lead Data Scientist will operate with broad autonomy, manage workstream plans and risks, and bring major methodological, governance, or cross-platform decisions to the VP of AI and VP Analytics when a decision has broader business impact.

In addition to delivering models, the Lead Data Scientist will help build internal AI products and contribute improvements to shared practices for temporal validation, explainability, responsible AI and data use, model governance, and performance monitoring. Working with the VP of AI and VP Analytics, the role will align assigned work streams to the broader scientific roadmap and escalate decisions with cross-workstream impact.

The role will partner with Business, AI, and Engineering to translate complex evidence into clear recommendations and measurable business outcomes.

Key Responsibilities:

• Own end-to-end delivery and measurable outcomes for assigned predictive underwriting and pricing work streams, from problem framing through deployment, monitoring, and continuous improvement, including:
  • Frame evidence-based recommendations and workstream trade-offs across model quality, risk, cost, scalability, aligning partners on delivery and measurable outcomes
  • Defining and documenting the Analytics-Ready Dataset, data-quality, and reusable feature requirements needed for assigned work streams across claims, pharmacy, utilization, financial, underwriting, and external data
  • Applying rigorous point-in-time development and out-of-time validation approaches for claims maturity, seasonality, leakage, stability, and uncertainty
  • Developing, comparing, and challenging predictive models, distributions, and hybrid rule/model approaches based on evidence and operating constraints
  • Balance near-term delivery with disciplined exploration of emerging methods, including deep learning or GenAI solutions, that can materially improve accuracy, scalability, decision quality, or operating efficiency
  • Translating model needs into detailed feature requirements; partnering with business teams to identify additional signals and with Legal to secure approvals
  • Managing third-party model evaluations and ROI analyses when external expertise or independent validation is needed
  • Producing explainable, reproducible model outputs and following shared documentation, testing, monitoring, retraining, and rollback standards while recommending improvements based on workstream experience
• Champion reuse, standardization, and componentization of data science assets so successful features, pipelines, evaluation patterns, and scoring capabilities can scale…